descriptive part 1

theme_park = read_csv("ultimate data.csv") |> 
  janitor::clean_names()

## Rows: 920 Columns: 7
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): Park_Name, City, Country, Type, Region
## dbl (2): Year, Attendance
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

theme_park  |> 
    filter(
      region != c("Worldwide")
    ) |> 
    group_by(year, type) |> 
    mutate(
      attendance = attendance / 100000
    ) |> 
    summarise(mean = mean(attendance),
              sum = sum(attendance)) |> 
    knitr::kable(digits = 3)

## `summarise()` has grouped output by 'year'. You can override using the
## `.groups` argument.

year	type	mean	sum
2019	Amusement/Theme Park	542.806	37996.4
2019	Museum	335.013	20100.8
2019	Water Park	98.315	5898.9
2020	Amusement/Theme Park	186.159	13031.1
2020	Museum	77.742	4664.5
2020	Water Park	38.558	2313.5
2021	Amusement/Theme Park	320.910	22463.7
2021	Museum	107.650	6459.0
2021	Water Park	57.892	3473.5
2022	Amusement/Theme Park	425.616	21280.8
2022	Museum	193.388	11603.3
2022	Water Park	77.972	4678.3

theme_park |> 
  mutate(
    year = as.factor(year)
  ) |> 
  group_by(year) |> 
  plot_ly(y = ~attendance, color = ~year, type = "box", colors = "viridis")

 theme_park|> 
  filter(
    region != c("Worldwide")
  ) |> 
  group_by(region, year) |> 
  summarize(attend_sum = mean(attendance)) |> 
  plot_ly(x = ~year, y = ~attend_sum, color = ~region,
          type = "scatter", mode = 'point', colors = "viridis")

## `summarise()` has grouped output by 'region'. You can override using the
## `.groups` argument.